Data Management and Visualisation Project: Forest Research

## Should the below list of packages need to be installed, remove '#'(s) and run:
#libraries<-c("tidyverse", "cowplot", "magick", "readODS", "here", "plotly", "highcharter", "htmlwidgets")
#install.packages(libraries, repos="http://cran.rstudio.com")

## NECESSARY PACKAGES:

library(here)         # to create user-specific filepaths
library(readODS)      # to retrieve data from ODS files
library(tidyverse)    # for various visualisation packages
library(cowplot)      # for various visualisation options
library(magick)       # to import images onto visualisations
library(plotly)       # to create interactive scatterplots
library(highcharter)  # to create interactive barplots
library(htmlwidgets)  # to save interactive visualisations

## DATA PREPARATION:
# Extraction of raw data from ODS file

country_names<-c("England","Wales","Scotland","Northern Ireland")
pathway<-paste0(here("raw_secondary_data", "area-timeseries-20jun24.ods"))
countries_list<-list()
for (i in seq_along(country_names)){
  countries<-country_names[i]
  countries_list[[countries]]<-read_ods(pathway, sheet = i+3)
} # this loop extracts all of the raw data from the country-specific sheets and imports it into R
raw_extracted_data<-data.frame(countries_list) # which is then put into a dataframe

# Processing and cleaning of data

processed_extracted_data<-raw_extracted_data[-c(1:3),] # removes unnecessary text
names(processed_extracted_data)<-as.matrix(processed_extracted_data[1,]) # labels each column by their original titles
processed_extracted_data<-processed_extracted_data[-1,] # removes text names from the data
names(processed_extracted_data)<-make.unique(names(processed_extracted_data)) # makes each column unique
processed_extracted_data<-processed_extracted_data %>% select(-starts_with("Note")) # removes erroneous "note" columns
processed_extracted_data<-processed_extracted_data%>% mutate_if(is.character, as.numeric) # converts all variables into numeric form
rownames(processed_extracted_data) <- NULL # corrects for the erroneous row numbers extracted when subsetting from the raw data

# Mutual code for all visualisations
fig_path<-here("figs") # creates the necessary path for saving the figures
logo_file<-paste0(here("logo","Picture1.jpg")) # creates the path for applying the logo
year_ending_March_31st<-processed_extracted_data$`Year ending 31 March` # timeframe for visualisations

# This first plot, aptly named 'Basic Plot', was created while at the University of Sheffield as part of initial novice attempts at writing code, examined during the PSY6422 Module on the 'Psychological Research Methods with Data Science' MSc Course (2023-24).

## DATA EXTRACTION: 
# Extraction of necessary variables from processed dataframe

country_names<-c("England", "Wales", "Scotland", "Northern Ireland")
woodland_area<-select(processed_extracted_data, ends_with(" total (thousand ha)")) # Total Woodland Area
for (country in country_names){
  assign(country, woodland_area[[paste0(country, " total (thousand ha)")]])
} # creates numeric variables for the woodland area of each country, to be labelled per year

woodland_area<-data.frame(England,Wales,Scotland,`Northern Ireland`) # which is then put back into the dataframe
woodland_area<-woodland_area%>% rename(Northern_Ireland=`Northern.Ireland`) # *corrects for interaction issues now caused by spacing in `Northern Ireland`
country_names<-c("England", "Wales", "Scotland", "Northern_Ireland") # *

woodland_by_year<-cbind(year_ending_March_31st,woodland_area) # Total Woodland Area, By Year

# Calculation of proportional change in woodland area per country
percentage_results<-data.frame(country=character(),percentage_increase=numeric(),stringsAsFactors=FALSE) # creates an empty dataframe
for(country in country_names){
  min_v<-min(woodland_area[[country]])
  max_v<-max(woodland_area[[country]])
  percentage_increase<-(((max_v-min_v)/min_v)*100)
  percentage_results<-rbind(percentage_results, data.frame(country=country,percentage_increase=percentage_increase))
} # this loop calculates the percentage increase in woodland area of each country from 1998-2024
percentage_results[1:4,2]<-round(percentage_results[1:4,2],2) # then rounds the data to 2 decimal places

## FINAL DATAFRAME:
woodland_growth_over_time<-data.frame(
  country=c(rep("England",27),rep("Wales",27),rep("Scotland",27),rep("Northern Ireland",27)),
  woodland=c(woodland_by_year$England,woodland_by_year$Wales,
             woodland_by_year$Scotland,woodland_by_year$Northern_Ireland),
  year=c(woodland_by_year$year_ending_March_31st)) # creates a final dataframe amenable to the upcoming visualisation

mapping<-aes(x=year,y=woodland,colour=country) # creates the mapping for the visualisations

## BASIC STATIC PLOT:
# Creates a plot mapping the amount of woodland area development from 1998-2024, as divisable by country, and as annotated with percentage increase

BasicPlot<-woodland_growth_over_time %>%
  ggplot(mapping=mapping)+
  geom_smooth(method="gam")+
  geom_point()+
  labs(x="Year (ending March 31st)",
       y="Woodland area (in thousand hectares)",
       colour="Country",
       title="The Growth of Total Woodland Area within the United Kingdom",
       subtitle="As annotated with percentage increase from 1998-2024",
       caption="Data retrieved from: Forest Research, 2024")+
  annotate("label",x=2010,y=1210,label=paste(percentage_results[1,2],"%"),colour="#EE0000",size=3,fontface="bold")+
  annotate("label",x=2010,y=375,label=paste(percentage_results[2,2],"%"),colour="#00CD00",size=3,fontface="bold")+
  annotate("label",x=2010,y=1450,label=paste(percentage_results[3,2],"%"),colour="#0000CD",size=3,fontface="bold")+
  annotate("label",x=2010,y=175,label=paste(percentage_results[4,2],"%"),colour="#FFA500",size=3,fontface="bold")+
  scale_colour_manual(values=c(England="#EE0000",Wales="#00CD00",
                               Scotland="#0000CD",`Northern Ireland`="#FFA500"))+
  scale_x_continuous(breaks=seq(1998,2024,5))+
  scale_y_continuous(breaks=seq(0,1500,150))+
  theme(panel.border=element_rect(colour="#8B7355",fill=NA,linewidth=2),
        panel.grid.minor=element_line(colour="#8B7355",linewidth=0.5),
        panel.grid.major=element_line(colour="#CAFF70",linewidth=0.7),
        panel.background=element_rect(fill="#FFFFF0"),
        axis.line=element_line(linewidth=2,colour="#8B7355"),
        plot.title=element_text(face="bold"),
        plot.subtitle=element_text(face="italic"),
        text=element_text(family="serif"),
        legend.title=element_text(face="bold"),
        legend.box.background=element_rect(colour="#8B7355"),
        legend.box.margin=margin(1,1,1,1),
        legend.key=element_rect(colour="#8B7355"))

# To demonstrate the ability to do so, this code adds the official logo to sit alongside the data source

BasicPlot<-ggdraw(BasicPlot)+
  draw_image(logo_file, scale=.2,x=1,hjust=1,halign=1,valign=0)

## Visualisation of the Growth of Total Woodland Area within the United Kingdom, from 1998 to 2024

BasicPlot

# DATA MANIPULATION: Woodland Tree Types on both PUBLIC and PRIVATE land ...

total_trees<-cbind(public_trees,private_trees) # combines all data into one dataframe
names(total_trees)<-make.names(names(total_trees), unique=TRUE) # renders names unique to allow renaming
total_trees<-total_trees%>% 
  rename(private_woodland=`woodland.1`,public_woodland=woodland)%>% # renames variables to facilitate interaction
  mutate(sources=paste(tree_type,`tree_type.1`, sep=" + "))%>% # creates variable to record source of woodland area
  select(-c(1,4,6))%>% # removes now unneccessary variables from the dataframe
  select(c("sources", "year", "public_woodland", "private_woodland")) # reorders dataframe to improve readability
total_trees$total_woodland<-rowSums(total_trees[, c("public_woodland","private_woodland")], na.rm=TRUE) # calculates total woodland areas

visual_theme<-hc_theme( # creates an aesthetically similar "woodland"-esque theme to the prior visualisations
  colors=c("#FF0000","darkred","#00CD00","darkgreen","#0000CD","darkblue","#FFA900","darkorange"),
  chart=list(plotBackgroundColor="beige",
             style=list(fontFamily="Helvetica Neue", fontSize="15px")),
  title=list(style=list(fontWeight="bold",fontSize="20px")),
  yAxis=list(gridLineColor="#8B7355"))

# BASIC INTERACTIVE PLOT 3:

# Generates an interactive stacked barplot using the 'highcharter' rather than 'plotly' package, showing totals of coniferious and deciduous woodland area within the United Kingdom from 1998-2024

amalgamated_visualisation<-total_trees %>% 
  hchart('column', hcaes(x=year,y=total_woodland,group=sources),stacking="normal")%>%
  hc_title(text="Documented Woodland Area of the UK from 1998-2024")%>%
  hc_subtitle(text="Segmented by tree type (coniferous or deciduous) and country")%>%
  hc_xAxis(title=list(text="Year (ending March 31st)"))%>%
  hc_yAxis(title=list(text="Woodland area (in thousand hectares)"))%>%
  hc_add_theme(visual_theme)%>%
  hc_caption(text="Northern Ireland only began documenting woodland area types as of 2005: see abline")%>%
  hc_annotations(list(shapes=list(list(type = 'path',points = list(list(xAxis = 0, yAxis = 0, x = 2004.5, y = 0),
                                                                   list(xAxis = 0, yAxis = 0, x = 2004.5, y = 4000)),
                                       stroke="black",strokeWidth=1)),draggable=""))

# Trend in RECORDED woodland area (i.e. as 1998-2004 NI woodland area was not documented) in the United Kingdom from 1998-2024.

amalgamated_visualisation